yt_dlp/extractor/watchbox.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     strip_or_none,
  11     try_get,
  12     unescapeHTML,
  13     unified_timestamp,
  14 )
  15
  16
  17 class WatchBoxIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:www\.)?watchbox\.de/(?P<kind>serien|filme)/(?:[^/]+/)*[^/]+-(?P<id>\d+)'
  19     _TESTS = [{
  20         # film
  21         'url': 'https://www.watchbox.de/filme/free-jimmy-12325.html',
  22         'info_dict': {
  23             'id': '341368',
  24             'ext': 'mp4',
  25             'title': 'Free Jimmy',
  26             'description': 'md5:bcd8bafbbf9dc0ef98063d344d7cc5f6',
  27             'thumbnail': r're:^https?://.*\.jpg$',
  28             'duration': 4890,
  29             'age_limit': 16,
  30             'release_year': 2009,
  31         },
  32         'params': {
  33             'format': 'bestvideo',
  34             'skip_download': True,
  35         },
  36         'expected_warnings': ['Failed to download m3u8 information'],
  37     }, {
  38         # episode
  39         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-1/date-in-der-hoelle-328286.html',
  40         'info_dict': {
  41             'id': '328286',
  42             'ext': 'mp4',
  43             'title': 'S01 E01 - Date in der Hölle',
  44             'description': 'md5:2f31c74a8186899f33cb5114491dae2b',
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'duration': 1291,
  47             'age_limit': 12,
  48             'release_year': 2010,
  49             'series': 'Ugly Americans',
  50             'season_number': 1,
  51             'episode': 'Date in der Hölle',
  52             'episode_number': 1,
  53         },
  54         'params': {
  55             'format': 'bestvideo',
  56             'skip_download': True,
  57         },
  58         'expected_warnings': ['Failed to download m3u8 information'],
  59     }, {
  60         'url': 'https://www.watchbox.de/serien/ugly-americans-12231/staffel-2/der-ring-des-powers-328270',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         mobj = self._match_valid_url(url)
  66         kind, video_id = mobj.group('kind', 'id')
  67
  68         webpage = self._download_webpage(url, video_id)
  69
  70         player_config = self._parse_json(
  71             self._search_regex(
  72                 r'data-player-conf=(["\'])(?P<data>{.+?})\1', webpage,
  73                 'player config', default='{}', group='data'),
  74             video_id, transform_source=unescapeHTML, fatal=False)
  75
  76         if not player_config:
  77             player_config = self._parse_json(
  78                 self._search_regex(
  79                     r'playerConf\s*=\s*({.+?})\s*;', webpage, 'player config',
  80                     default='{}'),
  81                 video_id, transform_source=js_to_json, fatal=False) or {}
  82
  83         source = player_config.get('source') or {}
  84
  85         video_id = compat_str(source.get('videoId') or video_id)
  86
  87         devapi = self._download_json(
  88             'http://api.watchbox.de/devapi/id/%s' % video_id, video_id, query={
  89                 'format': 'json',
  90                 'apikey': 'hbbtv',
  91             }, fatal=False)
  92
  93         item = try_get(devapi, lambda x: x['items'][0], dict) or {}
  94
  95         title = item.get('title') or try_get(
  96             item, lambda x: x['movie']['headline_movie'],
  97             compat_str) or source['title']
  98
  99         formats = []
 100         hls_url = item.get('media_videourl_hls') or source.get('hls')
 101         if hls_url:
 102             formats.extend(self._extract_m3u8_formats(
 103                 hls_url, video_id, 'mp4', entry_protocol='m3u8_native',
 104                 m3u8_id='hls', fatal=False))
 105         dash_url = item.get('media_videourl_wv') or source.get('dash')
 106         if dash_url:
 107             formats.extend(self._extract_mpd_formats(
 108                 dash_url, video_id, mpd_id='dash', fatal=False))
 109         mp4_url = item.get('media_videourl')
 110         if mp4_url:
 111             formats.append({
 112                 'url': mp4_url,
 113                 'format_id': 'mp4',
 114                 'width': int_or_none(item.get('width')),
 115                 'height': int_or_none(item.get('height')),
 116                 'tbr': int_or_none(item.get('bitrate')),
 117             })
 118         self._sort_formats(formats)
 119
 120         description = strip_or_none(item.get('descr'))
 121         thumbnail = item.get('media_content_thumbnail_large') or source.get('poster') or item.get('media_thumbnail')
 122         duration = int_or_none(item.get('media_length') or source.get('length'))
 123         timestamp = unified_timestamp(item.get('pubDate'))
 124         view_count = int_or_none(item.get('media_views'))
 125         age_limit = int_or_none(try_get(item, lambda x: x['movie']['fsk']))
 126         release_year = int_or_none(try_get(item, lambda x: x['movie']['rel_year']))
 127
 128         info = {
 129             'id': video_id,
 130             'title': title,
 131             'description': description,
 132             'thumbnail': thumbnail,
 133             'duration': duration,
 134             'timestamp': timestamp,
 135             'view_count': view_count,
 136             'age_limit': age_limit,
 137             'release_year': release_year,
 138             'formats': formats,
 139         }
 140
 141         if kind.lower() == 'serien':
 142             series = try_get(
 143                 item, lambda x: x['special']['title'],
 144                 compat_str) or source.get('format')
 145             season_number = int_or_none(self._search_regex(
 146                 r'^S(\d{1,2})\s*E\d{1,2}', title, 'season number',
 147                 default=None) or self._search_regex(
 148                     r'/staffel-(\d+)/', url, 'season number', default=None))
 149             episode = source.get('title')
 150             episode_number = int_or_none(self._search_regex(
 151                 r'^S\d{1,2}\s*E(\d{1,2})', title, 'episode number',
 152                 default=None))
 153             info.update({
 154                 'series': series,
 155                 'season_number': season_number,
 156                 'episode': episode,
 157                 'episode_number': episode_number,
 158             })
 159
 160         return info